> ## Documentation Index > Fetch the complete documentation index at: https://offthepace.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Drivers: isolating skill from the car, nine ways > Nine features that each strip a different confound out of raw lap times to leave a signal that reflects the driver rather than the machinery career ratings, circuit and weather affinity, workload, and head-to-head duels. ## What this pillar does Every feature here attacks the same confound: in Formula 1, the car and the driver are almost perfectly correlated, so raw pace rankings are mostly a car ranking. The Drivers pillar isolates the driver's contribution using multiple independent identification strategies, each reading a different signal: * **Rating chains.** Era Ratings Timeline and Era Translator read `int_era_normalized_driver_rating`, a four-stage pipeline (car FE → LORO teammate baseline → Bayesian shrinkage → era bridge) that produces one comparable number per driver per season across the 2022 regulation boundary. * **Circuit and weather slices.** Driver Circuit Affinity, Wet-Race Specialist, and workload features ask a narrower question at a specific grain a circuit, a weather condition, or a traffic pattern. * **Pairwise.** Synthetic Teammate and Quali vs Race read the driver's own residual against a tightly controlled comparator (a synthesized same-car teammate, or the driver's own qualifying signal vs their race signal), eliminating the car by construction. * **Technique.** Corner-Phase Skill uses braking and mid-corner deviations relative to the driver's own car baseline so technique is isolated even within the same chassis. The Transform [Skill](/transform/families/skill) family page explains the de-biasing pipeline in full. ## Every feature in this pillar Each driver's era-adjusted pace rating across seasons, corrected for the 2022 regulation change and shown with honest confidence ribbons. A season leaderboard of era-adjusted driver ratings on one comparable scale, anchored by drivers who raced on both sides of the 2022 rule change. How reliably each driver extracts pace from the car, lap to lap, using the residual skill signal from the seven-term decomposition. Each driver's skill residual in qualifying plotted against their skill in the race, separating one-lap merchants from drivers who come alive over a stint. How much faster or slower each driver is at a specific circuit, relative to their own season average, after removing car and field effects. Each driver's wet-weather edge: race skill residual in the wet minus their dry baseline, across their full 2018–2024 career. Four tyre and traffic stress signals aggregated per driver per season push, stint age, dirty-air share, and cliff risk revealing who races hardest on their rubber. A pace comparison that weight-corrects each driver against a synthetic teammate, isolating pure skill from strategy and track-position effects. A skill index built from braking, mid-corner, and exit deviations relative to each driver's own car baseline so a fast car can't flatter a driver.